brenda-database
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the official BRENDA database (brenda-enzymes.org) to retrieve scientific data via its SOAP API.
- [COMMAND_EXECUTION]: The provided Python scripts include functionality to create directories and export research data to local files in CSV, JSON, PNG, and TXT formats.
- [PROMPT_INJECTION]: The skill processes data from a remote API which presents an indirect prompt injection surface. (1) Ingestion points: Enzyme data retrieved from the SOAP API in scripts/brenda_queries.py. (2) Boundary markers: No explicit delimiters are used to separate API data from agent instructions. (3) Capability inventory: The skill can write to the local file system and perform network operations. (4) Sanitization: The scripts use regular expressions to parse and structure the API responses.
Audit Metadata